List your company

Research

Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 benchmarksPage 340 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Mathematical Problem SolvingAIME 2024nlpagents tool use54May 18, 2026
Language GenerationWikinlp54Mar 27, 2026
Traffic state diagram refinementI-24 MOTION INCEPTION VT v1.0 (test Nov 30, Dec 1, 2)computer vision54Mar 26, 2026
Multi-turn Visual Question AnsweringConvBenchmultimodalllm chat instruction54Mar 24, 2026
Medical Question AnsweringMedMCQAbio medicalnlp54Mar 19, 2026
Jailbreak DefenseJBCadversarial safety security54Mar 19, 2026
Mathematical ReasoningOlymBenchllm chat instructionnlp54Jun 23, 2026
Conditional Average Treatment Effect EstimationSimulation study n1=250tabular time series54Mar 19, 2026
3D Semantic Occupancy PredictionOcc3D-nuScenes v1.0 (val)3d vision geometry54Jul 1, 2026
Language Model UnlearningTOFU (Forget10)llm chat instructionadversarial safety security54May 4, 2026
Node ClassificationComputers-Random (ρ ≈ 17.7)graph54Mar 18, 2026
Node ClassificationCS ρ ≈ 41.0 (random)graph54Mar 18, 2026
Machine UnlearningTOFU Forget 1%adversarial safety security54May 14, 2026
Large-scale Sparse Multi-objective OptimizationSMOP2miscellaneous54Jul 7, 2026
Large-scale Sparse Multi-objective OptimizationSMOP 1miscellaneous54Jul 7, 2026
Multi-hop Question AnsweringHotPotQAnlpretrieval search rag54Mar 13, 2026
General QANQnlp54May 11, 2026
Spike Sequence ClassificationNeuroMorsebio medical54Mar 11, 2026
Cross-modal Geo-localizationCVG-Text (New York)multimodalcomputer vision54Jun 23, 2026
Appearance ReconstructionWaymo 8 scenes3d vision geometry54Mar 10, 2026
Dataset-level accuracy estimationWikiSQL to Spider 2.0nlp54Mar 10, 2026
Dataset-level accuracy estimationSpider to SynSQL 2.5Mnlp54Mar 10, 2026
Dataset-level accuracy estimationSParC to CoSQLnlp54Mar 10, 2026
Dataset-level accuracy estimationWikiSQL to Spidernlp54Mar 10, 2026
Dataset-level accuracy estimationSpider to BIRDnlp54Mar 10, 2026